stable-diffusion-webui
stable-diffusion-webui copied to clipboard
AUTOMATIC1111
[Feature Request]: Option to print output image name with all parameters including seed
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What would your feature do ?
Allow to repeat the same prompt and generate similar images
Proposed workflow
- Run WebUI with a "include parameters in output name"
- Press Generate
- Image name is saved on a dated folder with the name including all parameters included
Additional information
No response
Generation parameters are saved in each image and can be retrieved with the PNG Info tab. There's also an option in Settings to save it in a text file.
Does that option work? I am on KDE. Will try it when the Cuda error is fixed on my install
I added the arguments: python launch.py --skip-torch-cuda-test --precision full --no-half
It ran with the CPU and I don't see anything on Gwenview
That's one of the options. Metadata/infotext is also embedded in the images by default. If you want to store the metadata in the filename there are also filename patterns. https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory
If you want something more specific feel free to re-open this, but I believe this should account for every case.
What I'm trying to find a way to do is have the generation data, or at least the prompt or selected parts of it, captioned in a lower corner on the face of the image itself. Maybe an option to save two images. One with and one without. That would be an awesome feature.
Is there an option or extension that prints all this data on the generated images either as a watermark over the actual image or on a border? Similar to what the X/Y plotter does... but I can control the data that is written to the image...
Like the old fashioned dat/time stamps on old point and shoot film cameras :D
Thank you.
